Active Parameters
313.3B
Context Length
1.05M
Modality
Text
Architecture
Mixture of Experts
KV Cache Rate
1440 KB/tok
License
MIT License
Release Date
25 Aug 2026
Knowledge Cutoff
-
API Pricing (per 1M)
Input: $0.15 · Output: $0.50
Precision
Context
Workload Memory: 629.54 GB
FP16 · 8K context
Base Weights: 615.79 GB
KV Cache: 11.25 GB
Runtime & Graphs: 2.50 GB
8x NVIDIA H200 141GB
629.5 / 1015.2 GB usable · TP 8
Determine requirements for your specific workload:
Upgrade to Pro
Checkpoint format
FP16
CUDA
>= 11.8
PyTorch
>= 2.1
Transformers
>= 5.16.0
| Architecture | Precision | Attention kernel |
|---|---|---|
Blackwell, Hopper | Native FP16 | FlashAttention-3 |
Ada Lovelace, Ampere | Native FP16 | FlashAttention-2 |
Rank
#84
| Benchmark | Score | Rank |
|---|---|---|
Agentic Index | 0.51 | 13 |
Agentic Coding | 0.57 | 22 |
Coding | 0.79 | 27 |
Data Analysis | 0.76 | 31 |
Web Development | 1610.48 | 35 |
Coding Index | 0.71 | 37 |
General Text | 1475 | 40 |
Agent Arena | 1045.63 | 46 |
General | 0.72 | 51 |
LiveBench Average | 0.72 | 51 |
Mathematics | 0.81 | 54 |
Reasoning | 0.78 | 57 |
Intelligence Index | 0.28 | 118 |
Overall Rank
#84
Coding Rank
#58
GLM-5.3 Flash is a high-efficiency open model designed for rapid inference and low-latency reasoning workloads. Built on the Glm5Next architecture, it offers optimized throughput for agentic applications and code generation.
Attention
Attention Structure
DeepSeek Sparse Attention
Attention Heads
64
Key-Value Heads
64
Attention Head Dimension
128
Position Embedding
ROPE
Linear Attention
Yes
Linear Attention Ratio
75.6%
Normalization
RMS Normalization
Activation Function
SwigLU
Dimensions
Base Precision
FP16
Hidden Dimension Size
4,096
Number of Layers
45
FFN Intermediate Size (Dense)
12,288
Multi-Token Prediction Heads
1
Tokenizer
Vocabulary Size
154,880
Mixture of Experts
Total Expert Parameters
17.3B
Number of Experts
288
Active Experts
8
Shared Experts
1
FFN Intermediate Size (per Expert)
2,048
Dense Layers Before MoE
3
General Language Models from Z.ai